CN111553365B - Question selection method and device, electronic equipment and storage medium - Google Patents
Question selection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111553365B CN111553365B CN202010366582.0A CN202010366582A CN111553365B CN 111553365 B CN111553365 B CN 111553365B CN 202010366582 A CN202010366582 A CN 202010366582A CN 111553365 B CN111553365 B CN 111553365B
- Authority
- CN
- China
- Prior art keywords
- question
- area
- target page
- page image
- naming
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010187 selection method Methods 0.000 title description 2
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000004590 computer program Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000003993 interaction Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 239000002775 capsule Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000001072 colon Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/164—File meta data generation
- G06F16/166—File name conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of question selection, and discloses a method, a device, electronic equipment and a storage medium for question selection. The method comprises the following steps: when a trigger instruction is received, acquiring a target page image and image coordinates of an operating body in the target page image; determining a question stem region by utilizing the image coordinates and the target page image, and judging the category of the question stem region; when the category is big, selecting all the small questions under the big questions as a selection area; when the category is a small question, obtaining a question type of the question stem area, and determining a selection area according to the question type; and selecting the title picture in the selected area. By implementing the embodiment of the invention, a small question or a question can be selected in a point contact mode, a user is not required to manually participate in cutting pictures of the content to be collected, the operation is simple and convenient, the question selection efficiency is improved, the user experience is improved, meanwhile, the problem stems and options are ensured to be simultaneously selected when aiming at a single small question, and the accuracy of the frame questions is improved.
Description
Technical Field
The invention relates to the technical field of question selection, in particular to a method, a device, electronic equipment and a storage medium for question selection.
Background
In order to solve the homework problems of middle and primary schools, a plurality of search questions or wrong question summarization application programs for solving the homework problems of students appear on the market at present, and the application programs all take question pictures through a camera to be stored as wrong questions or used for searching corresponding answers. The implementation methods are roughly divided into two main categories:
the first is to select the frame from the wanted questions manually or according to the operation track, and the frame is wanted to be operated for many times in such a way that the size of the frame is suitable, and the picture of the questions is obtained accurately.
The second method is based on that an operating body is used on the supporting body to select a point, then photographing is carried out according to the point, and a certain training model is used for obtaining a question picture based on a preset rule, which is more intelligent than the first method, but the method is very easy to select a question stem area, the option area is discarded, or a question stem of a certain question is selected, the actual question in the question is not selected, and the obtained frame selection area has little practical significance.
Disclosure of Invention
Aiming at the defects, the embodiment of the invention discloses a method, a device, electronic equipment and a storage medium for selecting questions, and a selection area is determined through question numbers and question types.
The first aspect of the embodiment of the invention discloses a method for selecting a question, which is applied to an intelligent terminal and comprises the following steps:
when a trigger instruction is received, acquiring a target page image and image coordinates of an operating body in the target page image;
determining a question stem region by using the image coordinates and the target page image, and judging the category of the question stem region;
when the category is a big question, selecting all the small questions under the big question as a selection area;
when the category is a small question, obtaining a question type of the question stem area, and determining a selection area according to the question type;
and selecting the title picture in the selected area.
In a first aspect of the embodiment of the present invention, when a trigger instruction is received, acquiring a target page image and image coordinates of an operating body in the target page image includes:
receiving an instruction sent by a user and judging whether the instruction is a trigger instruction or not;
when a trigger instruction is received, a camera is started to take a picture of the current page of the carrier, and the target page image is obtained;
and transforming the position coordinates of the operating body on the supporting body to obtain image coordinates of the position coordinates corresponding to the target page image.
In a first aspect of the embodiment of the present invention, determining a stem region using the image coordinates and the target page image, and determining a category of the stem region includes:
performing character recognition on the target page image;
determining the position of the question stem region in the target page image by utilizing the image coordinates and a preset rule;
acquiring the title number of the stem region and the auxiliary title number of N stems below the stem region, wherein N is more than 1;
determining naming rules corresponding to the target question number and the auxiliary question number;
if the number of the first naming rules is larger than that of the second naming rules, the category of the question stem area is a small question; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
In a first aspect of the embodiment of the present invention, selecting all the topics below the big topics as the selection area includes:
Obtaining a limit question number in the target page image, wherein the limit question number is the same as the naming rule of the target question number, the limit question number is positioned below the target question number, and no other question numbers with the same naming rule as the target question number exist between the limit question number and the target question number;
and taking the area between the question stem area and the limit question number as a selection area.
In a first aspect of the embodiment of the present invention, the method for obtaining the question type of the question stem area and determining the selection area according to the question type includes:
extracting topic features and keywords of the topic stem area;
judging the question type corresponding to the question stem area based on the question feature and the keyword;
when the question of the question stem area is a selection question, the question stem area and an option area corresponding to the question stem area are used as selection areas;
and when the question type of the question stem area is a non-selection question, taking the question stem area as a selection area.
In a first aspect of the embodiment of the present invention, the determining, based on the topic feature and the keyword, the topic shape corresponding to the topic stem area includes:
selecting a large number of topic samples, acquiring topic features and keywords of the topic samples, and taking topic types corresponding to the topic samples as labels;
Training the initial topic identification model by using the topic sample to obtain a trained topic identification model;
and inputting the topic characteristics and the keywords of the topic stem region into the topic type recognition model to obtain the topic type corresponding to the topic stem region.
The second aspect of the embodiment of the invention discloses a device for selecting a question, which is applied to an intelligent terminal and comprises the following components:
the device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a target page image and image coordinates of an operating body in the target page image when a trigger instruction is received;
the judging unit is used for determining a question stem area by utilizing the image coordinates and the target page image and judging the category of the question stem area;
the first determining unit is used for selecting all the topics under the big topics as selection areas when the categories are the big topics;
the second determining unit is used for acquiring the question type of the question stem area when the category is a small question, and determining a selection area according to the question type;
and the selecting unit is used for selecting the theme pictures in the selecting area.
In a second aspect of the embodiment of the present invention, as an optional implementation manner, the determining unit includes:
A character recognition subunit, configured to perform character recognition on the target page image;
the position determining subunit is used for determining the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
a question number acquisition subunit, configured to acquire a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
the rule determining subunit is used for determining naming rules corresponding to the target question number and the auxiliary question number;
the category judging subunit is used for judging the category of the question stem area as a small question if the number of the first naming rules is larger than that of the second naming rules; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
The third aspect of the embodiment of the invention discloses a method for selecting topics, which is applied to an intelligent terminal and a server and comprises the following steps:
When the intelligent terminal receives a trigger instruction, acquiring a target page image, and sending the target page image to a server;
the server determines the image coordinates of the operating body in the target page image, determines a stem area by utilizing the image coordinates and the target page image, and judges the category of the stem area;
when the category is a big problem, the server selects all the small problems under the big problem as a selection area;
when the category is a small question, the server acquires the question type of the question stem area and determines a selection area according to the question type;
and the server selects the title picture in the selected area.
In a third aspect of the embodiment of the present invention, the server determines an image coordinate of an operation body in the target page image, determines a stem area by using the image coordinate and the target page image, and determines a category of the stem area, including:
the server obtains an image coordinate of the position coordinate corresponding to the target page image through coordinate transformation of the position coordinate of the operation body on the supporting body;
the server carries out character recognition on the target page image;
The server determines the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
the server obtains the title number of the stem region and the auxiliary number of N stems below the stem region, wherein N is more than 1;
the server determines naming rules corresponding to the target question number and the auxiliary question number;
if the number of the first naming rules is larger than that of the second naming rules, the server judges that the category of the question stem area is a small question; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the server judges that the category of the question stem area is big questions; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
The fourth aspect of the embodiment of the invention discloses a device for selecting topics, which is applied to an intelligent terminal and a server and comprises the following components:
the acquisition unit is positioned in the intelligent terminal and is used for acquiring a target page image and transmitting the target page image to the server when receiving a trigger instruction;
The judging unit is positioned in the server and is used for determining the image coordinates of the operating body in the target page image, determining a question stem area by utilizing the image coordinates and the target page image and judging the category of the question stem area;
the first determining unit is positioned in the server and is used for selecting all the topics under the big topics as a selection area when the category is the big topics;
the second determining unit is positioned in the server and is used for acquiring the question type of the question stem area when the category is a small question and determining a selection area according to the question type;
and the selecting unit is positioned in the server and used for selecting the theme pictures in the selecting area.
In a fourth aspect of the present embodiment, as an optional implementation manner, the determining unit includes:
the coordinate conversion subunit is used for obtaining an image coordinate of the position coordinate corresponding to the target page image by transforming the position coordinate of the operating body on the supporting body through coordinates;
a character recognition subunit, configured to perform character recognition on the target page image;
the position determining subunit is used for determining the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
A question number acquisition subunit, configured to acquire a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
the rule determining subunit is used for determining naming rules corresponding to the target question number and the auxiliary question number;
the category judging subunit is used for judging the category of the question stem area as a small question if the number of the first naming rules is larger than that of the second naming rules; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
A fifth aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory to perform a method for topic selection as disclosed in the first aspect of the embodiments of the present invention.
A sixth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, where the computer program causes a computer to execute a method for selecting a topic disclosed in the first aspect of the embodiments of the present invention.
A seventh aspect of the embodiments of the present invention discloses a computer program product, which when run on a computer causes the computer to perform a method of topic selection as disclosed in the first aspect of the embodiments of the present invention.
An eighth aspect of the present embodiment discloses an application publishing platform, where the application publishing platform is configured to publish a computer program product, where the computer program product, when running on the computer, causes the computer to execute a method for selecting a topic disclosed in the first aspect of the present embodiment.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, when a trigger instruction is received, a target page image and image coordinates of an operating body in the target page image are acquired; determining a question stem region by using the image coordinates and the target page image, and judging the category of the question stem region; when the category is a big question, selecting all the small questions under the big question as a selection area; when the category is a small question, obtaining a question type of the question stem area, and determining a selection area according to the question type; and selecting the title picture in the selected area. Therefore, by implementing the embodiment of the invention, the selection area can be determined through the question number or the question number and the question type, so that a plurality of questions of the big questions can be selected simultaneously, the question selection efficiency is improved, the simultaneous selection of the questions and the options can be ensured when aiming at the single-channel questions, and the accuracy of the frame questions is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for selecting topics according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for topic selection according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a device for selecting questions according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another apparatus for selecting questions according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a system for selecting a topic according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a method, a device, electronic equipment and a storage medium for selecting a question, which can obtain a selection frame by constructing a first straight line and a second straight line according to a starting point coordinate and an ending point coordinate of a moving track, are simple and convenient to operate, can ensure the completeness of the question and improve the user experience, and are described in detail below with reference to the accompanying drawings.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a method for selecting questions according to an embodiment of the invention, wherein the question selection is performed in an intelligent terminal. The intelligent terminal comprises, but is not limited to, a learning machine, a home teaching machine, a point-reading machine, a tablet computer or a mobile phone. The question selection is used for storing the selected questions or searching the questions, the question storage can be applied to wrong question summarization or knowledge point summarization and the like, and the question searching is to search answers of the questions through the Internet after the question selection. As shown in fig. 1, the method for selecting the title includes the following steps:
110. And when a trigger instruction is received, acquiring a target page image and image coordinates of an operating body in the target page image.
The instruction is initiated by the user, which may be a user initiated by voice, for example: the "please help me save the question(s)" may be initiated by the user by touching a key or a mechanical key, or may be automatically triggered by the user opening some application program, such as a wrong question collection APP or a search question APP, which is not limited herein.
The instruction received by the intelligent terminal can be a question preservation instruction or a question searching instruction and the like, and the instructions are all used for preservation or searching after the question is selected on the premise of the question selection.
Before receiving the instruction, the camera and most devices of the intelligent terminal are in a sleep state, so that electric quantity can be saved, the intelligent terminal is awakened through the instruction, the intelligent terminal judges whether the instruction is an instruction for triggering question selection, and if so, the camera is started. The camera can be a front camera or a rear camera of the intelligent terminal, and also can be an external camera which is separated from the intelligent terminal and is in communication connection with the intelligent terminal.
The supporting body can be a book, an exercise book, a test paper and the like, and the operating body can be a finger, a touch pen, a pencil, a ruler, a small stick and the like. After the intelligent device receives the trigger instruction, the intelligent device can guide the user to place the position of the operating body in a voice interaction mode, and in the embodiment of the invention, the operating body is in point contact with the supporting body. For user positioning convenience, the point contact may be a contact point at a certain position of the stem of the question (for example, a blank on the lower side of the stem). This situation may present a problem, if the stem selected by the user is a stem (e.g., a first, selected question), then the stem is selected unambiguously, and it is actually representative that the user selects all the topics of the first question, any one of the user selects a stem of a selected question, and then selecting the question lacking the option is of little significance to the user.
In the invention, the user can intelligently identify the selected big or small questions. Specifically, no matter whether the user selects a big question or a small question, the camera integrally shoots the page of the user's question, and a target page image is obtained. Before the target page image is correspondingly processed, the target page image can be preprocessed first to ensure the accuracy of character recognition. Preprocessing includes, but is not limited to, denoising, contrast enhancement, shape correction and the like, wherein the shape correction mainly aims at the problem of camera view angle to shoot a trapezoid image or a curled carrier, the shape correction can be realized by stretching the edge of a target page image and the like, and the finally obtained target page image is rectangular.
After the corrected target page image is obtained, the position coordinates of the operating body on the supporting body are obtained through a coordinate conversion mode, and the coordinate conversion can be realized through an affine transformation algorithm. And obtaining the question stem area based on the position coordinates of the operation body on the target page image.
120. And determining a question stem region by using the image coordinates and the target page image, and judging the category of the question stem region.
And after the target page image and the image coordinates are obtained, character recognition is carried out on the target page image.
Character recognition may be achieved through mature OCR (Optical Character Recognition ) technology, characters including kanji, letters, punctuation, formulas, and the like. And determining the stem region by using the image coordinates and preset rules. For example, the preset rule may be that the upper position of the image coordinate is the stem region, at this time, the horizontal line where the image coordinate is located is the lower dividing line, the upper dividing line is determined by setting a threshold value based on the line interval between the topics being greater than the stem, and the region between the upper dividing line and the lower dividing line is the stem region, so as to obtain the stem region and the position of the stem region in the target page image.
The problem numbers are arranged in the problem stem area, the problem numbers in the problem stem area are identified as the title number, the problem numbers of N (N > 1) problem stems which appear below the problem stem area are identified as the auxiliary problem numbers, and whether the class of the problem stem area is big or small can be determined through the target problem numbers and the auxiliary problem numbers.
The question mark is realized through a certain question mark naming rule. The title naming convention may include, but is not limited to, the form of numeric characters (e.g., roman numerals, chinese numerals, etc.) plus punctuation characters (e.g., a break, comma, english period, colon, etc.), the form of numeric characters plus chinese brackets, etc., such as (1), (2), etc. Generally, chinese numerals are marked with punctuation marks as thematic categories, roman characters are marked with punctuation marks as thematic categories, and the form of numerals characters plus Chinese brackets is used as a sub-category of the thematic categories.
No matter what type of size questions is used herein, the size questions can be identified. The question number is generally located at the beginning position of the head line of the question stem area, the question number is obtained through character recognition of the beginning position of the head line, and the question number generally comprises more than two questions based on the big questions (if one big question only comprises one small question, the meaning of the existence of the big questions is not great).
One carrier generally adopts a naming rule of a big and small question, and based on this, the category of the question stem area can be obtained under the condition that the naming rule of the target question number and the auxiliary question number is determined.
If the number of the first naming rules is larger than that of the second naming rules, the category of the question stem area is a small question; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
Assuming that the question stem area is a big question, and at least comprises two small questions, if two auxiliary question numbers are selected, the number of naming rules of the big questions is 1, the number of naming rules of the small questions is 2, and the category of the question stem area can be reversely deduced to be the big question based on the judging mode; if three auxiliary question numbers are selected, the question stem area only comprises two questions, the number of naming rules of the questions is 2, and based on the judging mode, the categories of the question stem area can be reversely deduced to be the questions, and the like.
If the topic is located at the position of the front of the corresponding topic, the number of the selected auxiliary topic may be the same as the number of the topic naming rules, the number of the topic naming rules is definitely larger than the number of the topic naming rules, based on the judgment mode, the category of the topic stem area can be reversely deduced to be the topic, and an extreme example is that if the topic is located at the last topic of a topic, another topic is located below the topic, and because the other topic also at least comprises two topics, the number of the topic naming rules is still larger than the number of the topic naming rules no matter how the topic is selected.
And determining a selection area according to the category of the obtained question stem area, wherein the selection area is all the questions of the big question, and the selection area is all the contents of the questions. With specific reference to steps 130 and 140, respectively.
130. When the category is a big topic, all the small topics under the big topic are selected as selection areas.
The selected area of the topics is all the topics it contains. The step determines the upper dividing line of the stem region, and the upper dividing line of the stem region is also used as the upper dividing line of the selection region. Traversing the question numbers of the question stems below the question stem area to obtain the boundary question numbers which are the same as the naming rule of the target question numbers and are adjacent to the naming rule of the target question numbers, wherein no other question numbers with the same naming rule as the boundary question numbers and the target question numbers exist between the boundary question numbers and the target question numbers.
And selecting the area between the upper dividing line and the lower dividing line of the selection area by taking the upper blank area of the limit question number as the lower dividing line of the selection area, thus obtaining the selection area of the big question.
If no limit question number exists, all contents below the upper dividing line are taken as the selection area of the big questions.
140. And when the category is a small question, obtaining the question type of the question stem area, and determining a selection area according to the question type.
Normally, other question types generally do not include options except the option of the selected question, so in the embodiment of the invention, after the type corresponding to the question stem area is determined, the selected area is determined for the selected question and other question types respectively.
There are various ways of distinguishing the topic types.
Illustratively, the topic features and keywords of the stem region are obtained. The title feature may be content with underlines or brackets in chinese or blank areas, and the keywords may be: selecting, judging, filling, calculating, simply, proving and the like. And inputting the topic features and the keywords into a pre-trained topic recognition model to obtain the types corresponding to the topic stem regions. The topic identification model can be realized based on a convolutional neural network, and is obtained by selecting a large number of topic samples, taking topic types of the large number of topic samples as labels, and training topic features and keywords of the topic samples as input parameters.
The method can also be completed in an unsupervised training mode, namely characters in the stem region are converted into sentence feature vectors through character conversion (e.g. BERT), the sentence feature vectors are input into a pre-trained neural network recognition model (e.g. a capsule network) with constraint relation, the question type of the stem region is obtained, the capsule network recognition model is trained by taking the question type of a large number of question samples as labels, and the sentence feature vectors after the question sample conversion are taken as input parameters.
When the category of the question stem area is a small question and the corresponding question type is a selection question, the option area generally comprises options such as ABCD, the recognition technology of the part is mature, and the question stem area and the option area corresponding to the question stem area are taken as the selection area together.
And when the category of the question stem area is a small question and the corresponding question type is a non-selection question, the option area is directly used as the selection area.
In fact, for the selection area of the small questions, the method similar to the big questions can be adopted, the limit question numbers of the small questions are determined, the limit question numbers of the small questions are question numbers of any preset rules adjacent to each other below the small questions, a lower dividing line is arranged at a blank position above the limit question numbers, and the selection area of the small questions is formed between the lower dividing line and an upper dividing line of the question stem area.
150. And selecting the title picture in the selected area.
Selecting a question picture in the area, namely a target for selecting the questions, storing the question picture user as a wrong question collection or knowledge point collection, and searching the questions by removing the converted characters of the question picture to obtain answers of the questions corresponding to the question picture. For big questions, the method is used for searching questions by dividing the questions into different small images according to question numbers and searching the questions one by one. Therefore, the scene preferably used in the embodiment of the invention is the topic collection.
In order to better guide the user to select the title, after the user generates the trigger instruction, the intelligent terminal and the user are in a voice interaction mode to guide the user to position the contact point, for example, the voice interaction can be as follows: "if a question is to be selected, please put the finger in the blank area under the stem of the question, if a question is to be selected, please put the finger in the blank area under the stem of the question.
By implementing the embodiment of the invention, a small question or a question can be selected in a point contact mode, a user is not required to manually participate in cutting pictures of the content to be collected, the operation is simple and convenient, the question selection efficiency is improved, the user experience is improved, meanwhile, the problem stems and options are ensured to be simultaneously selected when aiming at a single small question, and the accuracy of the frame questions is improved.
Example two
Referring to fig. 2, fig. 2 is a flowchart illustrating another method for selecting a title according to an embodiment of the present invention, where the title selection is performed in an interaction between an intelligent terminal and a server. As shown in fig. 2, the method for selecting the title includes the following steps:
210. when the intelligent terminal receives the trigger instruction, acquiring a target page image, and sending the target page image to a server.
220. The server determines the image coordinates of the operating body in the target page image, determines the question stem area by utilizing the image coordinates and the target page image, and judges the category of the question stem area.
230. When the category is a big question, the server selects all the small questions under the big question as a selection area.
240. And when the category is a small question, the server acquires the question type of the question stem area and determines a selection area according to the question type.
250. And the server selects the title picture in the selected area.
Steps 210 to 250 described above are similar to steps 110 to 150 in the first embodiment. In the second embodiment, the coordinate conversion in step 110 and the content completed in the intelligent terminal in 120-150 are submitted to the server, and the preprocessing of the target page image can be completed in the intelligent terminal or/and the server. The method has the advantages that the question selection is completed through the interaction mode of the server and the intelligent terminal, the question selection efficiency can be improved, and the CPU occupation rate of the intelligent terminal is reduced.
Based on different frame questions of the user, the server also returns different operation results to the user: aiming at the question searching instruction, the server feeds back answers of the questions searching to the user; for the topic collection instruction, the server returns a storage result to the user, and the user can view the topics stored in the server database on the intelligent terminal.
By implementing the embodiment of the invention, a small question or a question can be selected in a point contact mode, a user is not required to manually participate in cutting pictures of the content to be collected, the operation is simple and convenient, the question selection efficiency is improved, the user experience is improved, meanwhile, the problem stems and options are ensured to be simultaneously selected when aiming at a single small question, and the accuracy of the frame questions is improved.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a device for selecting questions according to an embodiment of the present invention, which is applied to an intelligent terminal. As shown in fig. 3, the apparatus for selecting a title may include:
an obtaining unit 310, configured to obtain, when a trigger instruction is received, a target page image and image coordinates of an operating body in the target page image;
a judging unit 320, configured to determine a stem region by using the image coordinates and the target page image, and judge a category of the stem region;
A first determining unit 330, configured to select all topics under the topic as a selection area when the category is the topic;
a second determining unit 340, configured to obtain a question type of the question stem region when the category is a small question, and determine a selection region according to the question type;
and a selecting unit 350, configured to select the theme pictures in the selection area.
As an alternative embodiment, the obtaining unit 310 may include:
the instruction receiving subunit 311 is configured to receive an instruction sent by a user and determine whether the instruction is a trigger instruction;
the image obtaining subunit 312 is configured to, when receiving a trigger instruction, start a camera, and photograph a current page of the carrier to obtain the target page image;
and the coordinate conversion subunit 313 is configured to obtain, by coordinate transformation, an image coordinate of the position coordinate corresponding to the target page image from the position coordinate of the operation body on the carrier.
As an alternative embodiment, the determining unit 320 may include:
a character recognition subunit 321, configured to perform character recognition on the target page image;
a position determining subunit 322, configured to determine a position of the stem region in the target page image by using the image coordinates and a preset rule;
A question number acquisition subunit 323, configured to acquire a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
a rule determining subunit 324, configured to determine a naming rule corresponding to the target question number and the auxiliary question number;
a category determination subunit 325, configured to, if the number of the first naming rules is greater than the number of the second naming rules, determine a category of the stem area as a topic; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
As an alternative embodiment, the first determining unit 330 may include:
the limit question number obtaining subunit 331 is configured to obtain a limit question number in the target page image, where the limit question number is the same as a naming rule of the target question number, the limit question number is located below the target question number, and no other question numbers with the same naming rule as the target question number exist between the limit question number and the target question number;
The first area determining subunit 332 is configured to take the stem area and an area between the stem area and the boundary question number as the selection area.
As an alternative embodiment, the second determining unit 340 may include:
a feature extraction subunit 341, configured to extract topic features and keywords of the topic stem area;
the topic identification subunit 342 is configured to select a large number of topic samples, obtain topic features and keywords of the topic samples, and use topic types corresponding to the topic samples as labels; training the initial topic identification model by using the topic sample to obtain a trained topic identification model; inputting the topic characteristics and keywords of the topic stem area into the topic type recognition model to obtain a topic type corresponding to the topic stem area;
a second region determining subunit 343, configured to, when the question type of the question stem region is a selection question, take the question stem region and an option region corresponding to the question stem region as a selection region;
a third area determining subunit 344, configured to take the stem area as a selection area when the question type of the stem area is a non-selection question.
The device for selecting the questions shown in fig. 3 can select a question or a question in a point contact manner, does not need a user to manually participate in cutting pictures of the content to be collected, is simple and convenient to operate, improves the question selection efficiency, improves the user experience, and simultaneously ensures that the question stem and the option are simultaneously selected when aiming at a single-channel question, and improves the accuracy of the frame questions.
Example IV
Referring to fig. 4, fig. 4 is a schematic structural diagram of another device for selecting a question according to an embodiment of the present invention, which is applied to interaction between an intelligent terminal and a server. As shown in fig. 4, the apparatus for selecting a title may include:
an obtaining unit 410, located in the intelligent terminal 400, configured to obtain a target page image when receiving a trigger instruction, and send the target page image to a server;
a judging unit 510, located in the server 500, configured to determine an image coordinate of the operating body in the target page image, determine a stem area by using the image coordinate and the target page image, and judge a category of the stem area;
a first determining unit 520, located in the server 500, configured to select all the topics under the topic as a selection area when the category is the topic;
a second determining unit 530, located in the server 500, configured to obtain a question type of the question stem area when the category is a small question, and determine a selection area according to the question type;
a selecting unit 540, located in the server 500, for selecting the topic picture in the selected area.
As an alternative embodiment, the acquiring unit 410 may include:
An instruction receiving subunit 411, configured to receive an instruction sent by a user and determine whether the instruction is a trigger instruction;
the image obtaining subunit 412 is configured to start the camera when receiving the trigger instruction, and take a picture of the current page of the carrier to obtain the target page image;
an image sending subunit 413, configured to send the target page image to a server.
As an optional implementation manner, the determining unit 510 may include:
a coordinate conversion subunit 511, configured to obtain, by coordinate transformation, an image coordinate of the position coordinate of the operation body on the target page image, where the image coordinate corresponds to the position coordinate;
a character recognition subunit 512, configured to perform character recognition on the target page image;
a position determining subunit 513, configured to determine a position of the stem region in the target page image by using the image coordinates and a preset rule;
a question number obtaining subunit 514, configured to obtain a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
a rule determining subunit 515, configured to determine a naming rule corresponding to the target question number and the auxiliary question number;
A category determination subunit 516, configured to, if the number of the first naming rules is greater than the number of the second naming rules, determine a category of the stem area as a topic; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
As an alternative embodiment, the first determining unit 520 may include:
a limit question number obtaining subunit 521, configured to obtain a limit question number in the target page image, where the limit question number is the same as a naming rule of the target question number, the limit question number is located below the target question number, and no other question numbers with the same naming rule as the target question number exist between the limit question number and the target question number;
the first area determining subunit 522 is configured to take the stem area and an area between the stem area and the boundary question number as a selection area.
As an alternative embodiment, the second determining unit 530 may include:
A feature extraction subunit 531, configured to extract topic features and keywords of the topic stem region;
the topic identification subunit 532 is configured to select a large number of topic samples, obtain topic features and keywords of the topic samples, and use topic types corresponding to the topic samples as labels; training the initial topic identification model by using the topic sample to obtain a trained topic identification model; inputting the topic characteristics and keywords of the topic stem area into the topic type recognition model to obtain a topic type corresponding to the topic stem area;
a second region determining subunit 533, configured to, when the question type of the question stem region is a selection question, take the question stem region and an option region corresponding to the question stem region as selection regions;
and a third region determining subunit 534, configured to, when the question type of the question stem region is a non-selection question, take the question stem region as a selection region.
The device for selecting the questions shown in fig. 4 can select a question or a question in a point contact manner, does not need a user to manually participate in cutting pictures of the content to be collected, is simple and convenient to operate, improves the question selection efficiency, improves the user experience, and simultaneously ensures that the question stem and the option are simultaneously selected when aiming at a single-channel question, and improves the accuracy of the frame questions.
Example five
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic equipment can be intelligent terminals such as a learning machine, a home teaching machine, a point reading machine, a tablet personal computer or a mobile phone. As shown in fig. 5, the electronic device 600 may include:
a memory 610 storing executable program code;
a processor 620 coupled to the memory 610;
the processor 620 invokes the executable program code stored in the memory 610 to perform some or all of the steps of any of the methods of question selection of the first to second embodiments.
Example six
Referring to fig. 6, fig. 6 is a schematic diagram of a system for selecting questions according to an embodiment of the invention. As shown in fig. 6, the system 700 includes an intelligent terminal 710, which may be a learning machine, a home teaching machine, a point-to-read machine, a tablet computer, a cell phone, or the like, and a server 720. Wherein:
the intelligent terminal 710 may include: a memory 711 storing executable program codes; a processor 712 coupled to the memory 711; the processor 712 invokes executable program code stored in the memory 711 to perform the steps performed by the intelligent terminal in the method for selecting a topic in the second embodiment.
The server 720 may include: a memory 721 storing executable program code; a processor 722 coupled with the memory 721; the processor 722 invokes executable program code stored in the memory 721 to perform the steps performed by the server in the method for topic selection according to the second embodiment.
The embodiment of the invention discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute part or all of the steps of any one of the methods of the first to second embodiments.
The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute part or all of the steps of the method for selecting the questions in any one of the first embodiment to the second embodiment.
The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing a computer program product, and when the computer program product runs on a computer, the computer is caused to execute part or all of the steps in the method for selecting the title in any one of the first embodiment to the second embodiment.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data that is readable by a computer.
The above describes in detail a method, apparatus, electronic device and storage medium for selecting a title disclosed in the embodiments of the present invention, and specific examples are applied to illustrate the principles and embodiments of the present invention, where the above description of the embodiments is only for helping to understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The title selecting method is applied to an intelligent terminal and is characterized by comprising the following steps:
when a trigger instruction is received, acquiring a target page image and image coordinates of an operating body in the target page image;
determining a question stem region by using the image coordinates and the target page image, and judging the category of the question stem region;
when the category is a big question, selecting all the small questions under the big question as a selection area;
when the category is a small question, obtaining a question type of the question stem area, and determining a selection area according to the question type;
selecting the title picture in the selected area;
Determining a question stem region by using the image coordinates and the target page image, and judging the category of the question stem region, wherein the method comprises the following steps:
performing character recognition on the target page image;
determining the position of the question stem region in the target page image by utilizing the image coordinates and a preset rule;
acquiring the title number of the stem region and the auxiliary title number of N stems below the stem region, wherein N is more than 1;
determining naming rules corresponding to the target question number and the auxiliary question number;
if the number of the first naming rules is larger than that of the second naming rules, the category of the question stem area is a small question; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
2. The method according to claim 1, wherein when receiving the trigger instruction, acquiring the target page image and the image coordinates of the operation body in the target page image, comprises:
Receiving an instruction sent by a user and judging whether the instruction is a trigger instruction or not;
when a trigger instruction is received, a camera is started to take a picture of the current page of the carrier, and the target page image is obtained;
and transforming the position coordinates of the operating body on the supporting body to obtain image coordinates of the position coordinates corresponding to the target page image.
3. The method of claim 1, wherein selecting all topics below the topic as selection regions comprises:
obtaining a limit question number in the target page image, wherein the limit question number is the same as the naming rule of the target question number, the limit question number is positioned below the target question number, and no other question numbers with the same naming rule as the target question number exist between the limit question number and the target question number;
and taking the area between the question stem area and the limit question number as a selection area.
4. The method of claim 1, wherein obtaining a question type of the question stem region and determining a selection region according to the question type comprises:
extracting topic features and keywords of the topic stem area;
judging the question type corresponding to the question stem area based on the question feature and the keyword;
When the question of the question stem area is a selection question, the question stem area and an option area corresponding to the question stem area are used as selection areas;
and when the question type of the question stem area is a non-selection question, taking the question stem area as a selection area.
5. The method of claim 4, wherein determining a question type corresponding to the stem region based on the question feature and a keyword comprises:
selecting a large number of topic samples, acquiring topic features and keywords of the topic samples, and taking topic types corresponding to the topic samples as labels;
training the initial topic identification model by using the topic sample to obtain a trained topic identification model;
and inputting the topic characteristics and the keywords of the topic stem region into the topic type recognition model to obtain the topic type corresponding to the topic stem region.
6. The title selecting device is applied to an intelligent terminal, and is characterized in that the device comprises:
the device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a target page image and image coordinates of an operating body in the target page image when a trigger instruction is received;
the judging unit is used for determining a question stem area by utilizing the image coordinates and the target page image and judging the category of the question stem area;
The first determining unit is used for selecting all the topics under the big topics as selection areas when the categories are the big topics;
the second determining unit is used for acquiring the question type of the question stem area when the category is a small question, and determining a selection area according to the question type;
a selecting unit, configured to select a theme picture in the selection area;
the judging unit includes:
a character recognition subunit, configured to perform character recognition on the target page image;
the position determining subunit is used for determining the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
a question number acquisition subunit, configured to acquire a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
the rule determining subunit is used for determining naming rules corresponding to the target question number and the auxiliary question number;
the category judging subunit is used for judging the category of the question stem area as a small question if the number of the first naming rules is larger than that of the second naming rules; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
7. The title selecting method is applied to an intelligent terminal and a server and is characterized by comprising the following steps:
when the intelligent terminal receives a trigger instruction, acquiring a target page image, and sending the target page image to a server;
the server determines the image coordinates of the operating body in the target page image, determines a stem area by utilizing the image coordinates and the target page image, and judges the category of the stem area;
when the category is a big problem, the server selects all the small problems under the big problem as a selection area;
when the category is a small question, the server acquires the question type of the question stem area and determines a selection area according to the question type;
the server selects the title picture in the selected area;
the server determines the image coordinates of the operating body in the target page image, determines the question stem area by utilizing the image coordinates and the target page image, and judges the category of the question stem area, and the method comprises the following steps:
the server obtains an image coordinate of the position coordinate corresponding to the target page image through coordinate transformation of the position coordinate of the operation body on the supporting body;
the server carries out character recognition on the target page image;
The server determines the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
the server obtains the title number of the stem region and the auxiliary number of N stems below the stem region, wherein N is more than 1;
the server determines naming rules corresponding to the target question number and the auxiliary question number;
if the number of the first naming rules is larger than that of the second naming rules, the server judges that the category of the question stem area is a small question; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the server judges that the category of the question stem area is big questions; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
8. The title selecting device is applied to an intelligent terminal and a server, and is characterized in that: the device comprises:
the acquisition unit is positioned in the intelligent terminal and is used for acquiring a target page image and transmitting the target page image to the server when receiving a trigger instruction;
The judging unit is positioned in the server and is used for determining the image coordinates of the operating body in the target page image, determining a question stem area by utilizing the image coordinates and the target page image and judging the category of the question stem area;
the first determining unit is positioned in the server and is used for selecting all the topics under the big topics as a selection area when the category is the big topics;
the second determining unit is positioned in the server and is used for acquiring the question type of the question stem area when the category is a small question and determining a selection area according to the question type;
the selecting unit is positioned in the server and used for selecting the theme pictures in the selecting area;
the judging unit includes:
the coordinate conversion subunit is used for obtaining an image coordinate of the position coordinate corresponding to the target page image by transforming the position coordinate of the operating body on the supporting body through coordinates;
a character recognition subunit, configured to perform character recognition on the target page image;
the position determining subunit is used for determining the position of the question stem area in the target page image by utilizing the image coordinates and a preset rule;
a question number acquisition subunit, configured to acquire a question number of the question stem region and auxiliary question numbers of N question stems below the question stem region, where N is greater than 1;
The rule determining subunit is used for determining naming rules corresponding to the target question number and the auxiliary question number;
the category judging subunit is used for judging the category of the question stem area as a small question if the number of the first naming rules is larger than that of the second naming rules; if the number of the first naming rules is smaller than or equal to the number of the second naming rules, the category of the question stem area is a big question; the first naming rule is a naming rule corresponding to the target question number, the second naming rule is a naming rule different from the naming rule corresponding to the target question number in the auxiliary question number, and the sum of the number of the first naming rules and the number of the second naming rules is N+1.
9. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing a method of topic selection as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a method of topic selection as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010366582.0A CN111553365B (en) | 2020-04-30 | 2020-04-30 | Question selection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010366582.0A CN111553365B (en) | 2020-04-30 | 2020-04-30 | Question selection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553365A CN111553365A (en) | 2020-08-18 |
| CN111553365B true CN111553365B (en) | 2023-11-24 |
Family
ID=72003355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010366582.0A Active CN111553365B (en) | 2020-04-30 | 2020-04-30 | Question selection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553365B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270295A (en) * | 2020-11-13 | 2021-01-26 | 广东小天才科技有限公司 | Question framing method and device under student homework scene, terminal equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003255816A (en) * | 2002-02-28 | 2003-09-10 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for displaying examination picture, program for executing the method, and recording medium with the execution program recorded thereon |
| CN108133167A (en) * | 2016-12-01 | 2018-06-08 | 北京新唐思创教育科技有限公司 | A kind of automatic judging method and its device selected with judging topic answer |
| CN108304562A (en) * | 2018-02-08 | 2018-07-20 | 广东小天才科技有限公司 | Question searching method and device and intelligent terminal |
| CN110427412A (en) * | 2019-06-27 | 2019-11-08 | 深圳中兴网信科技有限公司 | Topic read method, device, topic input device and computer storage medium |
| CN110765995A (en) * | 2019-10-11 | 2020-02-07 | 深圳市鹰硕技术有限公司 | Answer sheet generation method, answer sheet identification device and storage medium |
| CN110837833A (en) * | 2019-11-14 | 2020-02-25 | 广东小天才科技有限公司 | Question selection method and device, terminal equipment and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207879B (en) * | 2012-01-17 | 2016-03-30 | 阿里巴巴集团控股有限公司 | The generation method and apparatus of image index |
-
2020
- 2020-04-30 CN CN202010366582.0A patent/CN111553365B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003255816A (en) * | 2002-02-28 | 2003-09-10 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for displaying examination picture, program for executing the method, and recording medium with the execution program recorded thereon |
| CN108133167A (en) * | 2016-12-01 | 2018-06-08 | 北京新唐思创教育科技有限公司 | A kind of automatic judging method and its device selected with judging topic answer |
| CN108304562A (en) * | 2018-02-08 | 2018-07-20 | 广东小天才科技有限公司 | Question searching method and device and intelligent terminal |
| CN110427412A (en) * | 2019-06-27 | 2019-11-08 | 深圳中兴网信科技有限公司 | Topic read method, device, topic input device and computer storage medium |
| CN110765995A (en) * | 2019-10-11 | 2020-02-07 | 深圳市鹰硕技术有限公司 | Answer sheet generation method, answer sheet identification device and storage medium |
| CN110837833A (en) * | 2019-11-14 | 2020-02-25 | 广东小天才科技有限公司 | Question selection method and device, terminal equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 孟祥丽等.纸质问卷版面设计与自动识别系统研究.《测控技术》.2018,第37卷(第8期),第32-35、45页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553365A (en) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105975560B (en) | Question searching method and device of intelligent equipment | |
| CN104268603B (en) | Intelligent marking method and system for text objective questions | |
| CN111753767A (en) | Method and device for automatically correcting operation, electronic equipment and storage medium | |
| CN111027537B (en) | Question searching method and electronic equipment | |
| CN103761892A (en) | Method and device for playing paper book contents in voice mode | |
| CN109933198B (en) | Semantic recognition method and device | |
| CN109783613B (en) | Question searching method and system | |
| CN107679070B (en) | Intelligent reading recommendation method and device and electronic equipment | |
| CN103903491A (en) | Method and device for realizing writing check | |
| CN111581367A (en) | Method and system for inputting questions | |
| CN111753120A (en) | Method and device for searching questions, electronic equipment and storage medium | |
| CN111711757B (en) | Test question shooting method and device capable of preventing finger from being blocked, electronic equipment and storage medium | |
| CN111524045A (en) | Dictation method and device | |
| CN112149680A (en) | Wrong word detection and identification method and device, electronic equipment and storage medium | |
| CN111553365B (en) | Question selection method and device, electronic equipment and storage medium | |
| CN111753168A (en) | Method and device for searching questions, electronic equipment and storage medium | |
| CN111563497B (en) | Frame question method and device based on moving track, electronic equipment and storage medium | |
| CN111079489B (en) | Content identification method and electronic equipment | |
| CN111582281B (en) | Picture display optimization method and device, electronic equipment and storage medium | |
| CN111711758B (en) | Multi-pointing test question shooting method and device, electronic equipment and storage medium | |
| CN112560728B (en) | Target object identification method and device | |
| CN111563498B (en) | Method and device for collecting questions, electronic equipment and storage medium | |
| CN113449652A (en) | Positioning method and device based on biological feature recognition | |
| CN111652204B (en) | Method, device, electronic equipment and storage medium for selecting target text region | |
| CN113420983A (en) | Writing evaluation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |